junos
/
rapids
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/carissalow/rapids

pull/95/head
nikunjgoel95 2020-08-05 12:09:52 -04:00
parent 8cfe2dabb7 eeeff354e6
commit 19b61a66aa
1 changed files with 27 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
docs/features/extracted.rst
View File

@ -489,17 +489,17 @@ features Features to be computed, see table below
**Available Activity Recognition Features**
====================== ============ =============
====================== ============== =============
Name Units Description
====================== ============ =============
====================== ============== =============
count rows Number of detect activity events (rows).
mostcommonactivity factor The most common activity.
mostcommonactivity activity_type The most common ``activity_type``. If this feature is not unique the first ``activity_type`` of the set of most common ``activity_types`` is selected ordered by ``activity_type``.
countuniqueactivities activities Number of unique activities.
activitychangecount transitions Number of transitions between two different activities; still to running for example.
sumstationary minutes The total duration of episodes of still and tilting (phone) activities.
summobile minutes The total duration of episodes of on foot, running, and on bicycle activities
sumvehicle minutes The total duration of episodes of on vehicle activity
====================== ============ =============
====================== ============== =============
**Assumptions/Observations:**
@ -507,6 +507,22 @@ iOS Activity Recognition data labels are unified with Google Activity Recognitio
In AWARE, Activity Recognition data for Google (Android) and iOS are stored in two different database tables, RAPIDS (via Snakemake) automatically infers what platform each participant belongs to based on their participant file (``data/external/``) which in turn takes this information from the ``aware_device`` table (see ``optional_ar_input`` function in ``rules/features.snakefile``).
The activties are mapped to activity_types as follows:
=============== ===============
Activity Name Activity Type
=============== ===============
in_vehicle 0
on_bicycle 1
on_foot 2
still 3
unknown 4
tilting 5
walking 7
running 8
=============== ===============
.. _light-doc:
Light